Compare models
Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.
- DeepSeek V4.1 FlashDeepSeekRemove
- Devstral MediumMistral AIRemove
- GLM 5.3 FlashZ.AIRemove
- GPT-6 AstraOpenAIRemove
4 is the maximum. Remove one to add another.
| Attribute | DeepSeek V4.1 Flashdeepseek-v4.1-flash | Devstral Mediumdevstral-medium | GLM 5.3 Flashglm-5.3-flash | GPT-6 Astragpt-6-astra |
|---|---|---|---|---|
| Pricing | ||||
| Input | $0.30 / 1M | $0.80 / 1M | $0.075 / 1M | $10.00 / 1M |
| Output | $1.20 / 1M | $4.00 / 1M | $0.25 / 1M | $50.00 / 1M |
| Cache Write (5m) | $0.30 / 1M | $0.80 / 1M | $0.075 / 1M | $10.00 / 1M |
| Cache Write (1h) | $0.30 / 1M | $0.80 / 1M | $0.075 / 1M | $10.00 / 1M |
| Cache Read | $0.30 / 1M | $0.80 / 1M | $0.075 / 1M | $10.00 / 1M |
| Web Search | $0 / 1M | $0 / 1M | $0 / 1M | $0 / 1M |
| Context | ||||
| Max context | 1M | 131.1K | 1M | 1M |
| Max output | N/A | N/A | N/A | N/A |
| Capabilities | ||||
| Vision | Yes | No | Yes | Yes |
| Function Calling | Yes | No | Yes | Yes |
| JSON Mode | Yes | No | Yes | Yes |
| Streaming | Yes | No | Yes | Yes |
| Catalogue | ||||
| Provider | DeepSeek | Mistral AI | Z.AI | OpenAI |
| Category | chat | chat | chat | chat |
| Charge type | Pay As You Go | Pay As You Go | Pay As You Go | Pay As You Go |
| Released | — | — | — | — |
| Description | ||||
| Summary | DeepSeek V4.1 Flash is a cost-efficient sparse Mixture-of-Experts (MoE) model in DeepSeek's V4.1 family, optimized for coding, reasoning, and agentic workflows. Despite its efficiency-focused positioning, DeepSeek reports that it surpasses the previous V4 Pro in performance, inference speed, and overall task completion time. The model is particularly strong at long-horizon, multi-step execution, making it well suited for coding agents, complex problem solving, and autonomous workflows that must reliably carry tasks through to completion. | — | GLM-5.3-Flash is Z.AI's efficient native multimodal model, designed for coding and long-horizon agentic workflows. It combines strong multimodal capabilities with an architecture optimized for responsive, cost-efficient task execution. Built on a hybrid sparse and linear attention architecture, GLM-5.3-Flash maintains accurate long-context behavior while reducing computational overhead, making it well suited for coding agents, extended multi-step tasks, and scalable production workloads. | GPT-6 Astra is OpenAI's flagship model for demanding end-to-end professional work, designed for advanced analysis, software engineering, deep research, scientific tasks, and document creation. It is particularly strong in long-horizon agentic workflows, including tasks that require sustained reasoning, tool orchestration, and computer and browser use, making it well suited for complex autonomous workflows and production-grade knowledge work. |